claude-dev-env 8.26.3 → 8.26.5

package/.agents/skills/{plugin-eval-standalone-skill → build-eval}/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: plugin-eval-standalone-skill
+name: build-eval
 description: >-
   Evaluate skills with a bounded direct Codex review suite or `claude plugin eval`.
   Use labeled inputs and deterministic grading for output correctness; use a plugin
@@ -7,7 +7,7 @@ description: >-
   Use when the user asks to eval or test a skill.
 ---
 
-# Plugin eval for a standalone skill
+# Build eval
 
 For building an evaluation of an AI workflow, follow [the design process](reference/build-evaluation.md).
 For a direct Codex output-quality evaluation, use [the review suite](evals/review/README.md).
@@ -100,7 +100,7 @@ Otherwise work the steps in order.
   and the `claude -p` recipe for flag-gated features.
 
 ```text
-plugin-eval-standalone-skill/
+build-eval/
 ├── SKILL.md
 └── reference/
     └── graders-and-commands.md

package/.agents/skills/{plugin-eval-standalone-skill → build-eval}/evals/review/README.md

@@ -21,9 +21,9 @@ Report finding precision and recall, clean-case specificity and false-positive r
 From the repository root:
 
 ```powershell
-$suite = 'packages/claude-dev-env/.agents/skills/plugin-eval-standalone-skill/evals/review/run.py'
+$suite = 'packages/claude-dev-env/.agents/skills/build-eval/evals/review/run.py'
 python $suite validate
-python -m pytest packages/claude-dev-env/.agents/skills/plugin-eval-standalone-skill/evals/review/test_run.py -q
+python -m pytest packages/claude-dev-env/.agents/skills/build-eval/evals/review/test_run.py -q
 python $suite live --limit 2 --timeout 90 --model gpt-6.1-sol --effort low --output review-smoke
 python $suite live --split heldout --limit 6 --timeout 90 --model gpt-6.1-sol --effort low --output review-heldout
 ```

package/.agents/skills/pull-request/SKILL.md

@@ -105,6 +105,20 @@ Check each behavior claim against the final diff and verification evidence.
 Preserve whether a rule is added, removed, or narrowed, and distinguish tests
 added from tests run. Refresh these claims after a rebase or correction.
 
+Open with the concrete problem and resulting behavior in one or two short
+paragraphs of plain prose. Write for a reviewer who has not read the worker's
+conversation. Include only claims supported by the final diff. State commands,
+results, and material limits under `## Verification`.
+
+Keep substantive review and test evidence. Put extensive logs, raw diffs, token
+counts, and agent transcripts in an existing linked artifact or a closed
+`<details>` section after the primary explanation. Let justified evidence grow
+without a total-length cap. A collapsed transcript still needs a useful opening.
+
+Load a repository's PR-description skill and run the checker command it supplies.
+Apply these steps to automated publishers too. A green code check proves no
+description claim by itself.
+
 ### 3. Run the local linter
 
 Resolve the active managed root (`CLAUDE_CONFIG_DIR` when set, `~/.claude`
@@ -158,6 +172,8 @@ without exposing author values.
 
 Confirm the published claims still describe the verified head and preserve the
 scope of its evidence, including whether checks used saved artifacts or a new run.
+Read the remote opening with evidence sections collapsed. Confirm that it explains
+the change on its own and that the evidence links lead to the cited results.
 
 ## Exit handling
 

package/bin/ever-shipped-skills.mjs

@@ -7,6 +7,7 @@ export const EVER_SHIPPED_SKILL_NAMES = new Set([
     'bdd-protocol',
     'beat-sheet',
     'bg-agent',
+    'build-eval',
     'build-goal-prompt',
     'bugteam',
     'caveman',

package/bin/ever-shipped-skills.test.mjs

@@ -1,6 +1,6 @@
 import { strict as assert } from 'node:assert';
 import { test } from 'node:test';
-import { existsSync, readdirSync } from 'node:fs';
+import { existsSync, readFileSync, readdirSync } from 'node:fs';
 import { dirname, join } from 'node:path';
 import { fileURLToPath } from 'node:url';
 import { EVER_SHIPPED_SKILL_NAMES } from './ever-shipped-skills.mjs';
@@ -41,7 +41,21 @@ test('EVER_SHIPPED_SKILL_NAMES includes the windows scheduled task skill', () =>
     assert.equal(EVER_SHIPPED_SKILL_NAMES.has('windows-scheduled-task'), true);
 });
 
-test('EVER_SHIPPED_SKILL_NAMES includes the plugin eval standalone skill', () => {
+test('build-eval ships under its matching name without the retired active directory', () => {
+    const sourceSkillsDirectory = join(
+        PACKAGE_DIRECTORY,
+        PACKAGE_AGENTS_HOME_DIRECTORY_NAME,
+        MANAGED_SKILLS_DIRECTORY_NAME,
+    );
+    assert.ok(EVER_SHIPPED_SKILL_NAMES.has('build-eval'));
+    assert.match(
+        readFileSync(join(sourceSkillsDirectory, 'build-eval', 'SKILL.md'), 'utf8'),
+        /^---\r?\nname: build-eval\r?\n/,
+    );
+    assert.equal(existsSync(join(sourceSkillsDirectory, 'plugin-eval-standalone-skill')), false);
+});
+
+test('EVER_SHIPPED_SKILL_NAMES retains the retired plugin eval standalone skill', () => {
     assert.equal(EVER_SHIPPED_SKILL_NAMES.has('plugin-eval-standalone-skill'), true);
 });
 

package/bin/install.prune.test.mjs

@@ -24,6 +24,7 @@ const RETIRED_SKILL_DIRECTORIES = [
     'fixbugs',
     'pr-scope-resolve',
     'post-audit-findings',
+    'plugin-eval-standalone-skill',
     'pr-consistency-audit',
     'bdd-protocol',
     'hitl',
@@ -607,6 +608,28 @@ test('a full reinstall over a pre-manifest dirty tree prunes retired skills and
     }
 });
 
+test('a full install replaces the retired plugin eval name with build-eval', () => {
+    const sandbox = createSandbox();
+    const retiredSkillName = 'plugin-eval-standalone-skill';
+    try {
+        plantSkillDirectory(sandbox.skillsDirectory, retiredSkillName, true);
+
+        runInstaller(sandbox.homeDirectory, []);
+
+        assert.equal(existsSync(join(sandbox.skillsDirectory, retiredSkillName)), false);
+        assert.ok(prunedSkillBackupContains(sandbox.claudeDirectory, retiredSkillName));
+        assert.match(
+            readFileSync(join(sandbox.skillsDirectory, 'build-eval', 'SKILL.md'), 'utf8'),
+            /^---\r?\nname: build-eval\r?\n/,
+        );
+        const manifest = readManifest(sandbox.manifestPath);
+        assert.ok(manifest.skills.includes('build-eval'));
+        assert.equal(manifest.skills.includes(retiredSkillName), false);
+    } finally {
+        rmSync(sandbox.homeDirectory, { recursive: true, force: true });
+    }
+});
+
 test('a full reinstall over an old-format manifest without a skills key still prunes via the ever-shipped fallback', () => {
     const sandbox = createSandbox();
     try {

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "claude-dev-env",
-    "version": "8.26.3",
+    "version": "8.26.5",
     "description": "Claude Code development standards — rules, hooks, agents, commands, and skills",
     "type": "module",
     "bin": {